JPS61175880A - Broken line extracting device - Google Patents

Broken line extracting device

Info

Publication number
JPS61175880A
JPS61175880A JP1788585A JP1788585A JPS61175880A JP S61175880 A JPS61175880 A JP S61175880A JP 1788585 A JP1788585 A JP 1788585A JP 1788585 A JP1788585 A JP 1788585A JP S61175880 A JPS61175880 A JP S61175880A
Authority
JP
Japan
Prior art keywords
broken line
lines
broken
horizontal
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
JP1788585A
Other languages
Japanese (ja)
Other versions
JPH0449148B2 (en
Inventor
Shinichi Matsui
真一 松居
Takayuki Kageyama
影山 尊之
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Panasonic Holdings Corp
Original Assignee
Matsushita Electric Industrial Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Matsushita Electric Industrial Co Ltd filed Critical Matsushita Electric Industrial Co Ltd
Priority to JP1788585A priority Critical patent/JPS61175880A/en
Publication of JPS61175880A publication Critical patent/JPS61175880A/en
Publication of JPH0449148B2 publication Critical patent/JPH0449148B2/ja
Granted legal-status Critical Current

Links

Abstract

PURPOSE:To extract broken lines at high speed and flexibly even from a picture in which graphic elements such as characters are mixed by binary coding a picture on the two-dimensional plane and inputting, making horizontal and vertical scanning on the input picture, extracting only broken line element constituting a broken line, analyzing their connectivity and recognizing the broken line. CONSTITUTION:Under the control of a controlling section 11, a reading section 12 inputs the graphic elements drawn on a two-dimensional plane as the binary picture of white and black and holds in a processed picture storing section 13. Connecting components in the black picture element area are classified by a line element extracting section 14 into elements of horizontal lines, vertical lines, oblique lines, characters and broken lines, and the data of broken line element are held in a broken line element storing section 15, and the data of the horizontal lines, the vertical lines and the oblique lines are held in a straight line storing section 16. A broken line recognizing section 17 judges the connectivity of data and recognizes the broken lines, and determines the data of broken lines together with the data of the storing section 16 and stores in a broken line storing section 18. At the same time, the broken line is displayed in a display unit 19.

Description

【発明の詳細な説明】 産業上の利用分野 本発明は、図形2図面の認識や理解などを行なう際画像
中に存在する破線を他の画像要素と分離して抽出する破
線抽出装置に関するものである。
DETAILED DESCRIPTION OF THE INVENTION Field of the Invention The present invention relates to a broken line extraction device that extracts broken lines existing in an image by separating them from other image elements when recognizing or understanding a figure 2 drawing. be.

従来の技術 近年、ワードプロセッサ等の普及により文書作成等の業
務が自動化される傾向にあり、表の作成等のために実線
、破線等の線を自動的に認識する必要が生じている。以
下図面を参照しながら、上述した破線の抽出装置に関し
て従来の一例を説明する。第8図は従来例の構成、第9
図は従来例の破線の構成要素である破線素の連結性判定
方法を示すものである。第8図において、1は画像を2
値化して入力する画像読取部、2は単連結な黒画素領域
を1画素幅の骨状の線で表わすようにする細線化部、3
は細線化された一つの領域内で角度が急激に変化する屈
曲点を抽出する屈曲点抽出部、4は細線化された各要素
の方向性を判定する方向判定部、5は連結すべき要素を
判定する連結性判定部である。また第2図において、a
、bはそれぞれ細線化された要素を、al 、a2.b
l 。
2. Description of the Related Art In recent years, with the spread of word processors and the like, there has been a tendency to automate tasks such as document creation, and it has become necessary to automatically recognize lines such as solid lines and broken lines for creating tables and the like. A conventional example of the above-mentioned broken line extraction device will be described below with reference to the drawings. Figure 8 shows the configuration of the conventional example;
The figure shows a conventional method for determining the connectivity of broken line elements that are constituent elements of broken lines. In Figure 8, 1 is the image 2
2 is an image reading unit that converts the value into a value and inputs the data; 2 is a thinning unit that represents a simply connected black pixel area with a bone-like line with a width of 1 pixel; 3
4 is a bending point extraction unit that extracts a bending point where the angle suddenly changes within one thinned area, 4 is a direction determination unit that determines the directionality of each thinned element, and 5 is an element to be connected. This is a connectivity determination unit that determines. Also, in Figure 2, a
, b represent the thinned elements, al , a2 . b
l.

b2はa及びbの両端点を、θはaとbのなす角度を表
わす。第8図のように構成された破線抽出装置について
、以下その動作を説明する。
b2 represents both end points of a and b, and θ represents the angle formed by a and b. The operation of the broken line extraction device configured as shown in FIG. 8 will be described below.

まず、1の画像読取部において対象画像を2値化して画
像用メモリに入力する。次に2の細線化部において、入
力画像のすべての単連結黒画素領域を細線化する。この
とき、一定のしきい値以下の長さを持つ細線化された要
素について、以下3の屈曲点抽出部で角度の急変する個
所を検出し、両端点と分岐点、さらに上記屈曲点が新た
な端点となるように、必要ならば要素を複数に分割する
First, an image reading section 1 binarizes a target image and inputs it into an image memory. Next, in the thinning section 2, all singly connected black pixel areas of the input image are thinned. At this time, for the thinned element whose length is less than a certain threshold, the point where the angle suddenly changes is detected by the bending point extraction part 3 below, and both end points, branching points, and the above bending point are newly added. Divide the element into multiple parts if necessary so that the endpoints are correct.

4の方向判定部では要素の両端点座標から要素の方向を
決定する。最後に5の連結性判定部において、各要素の
連結性の判定を行なう。上記の連結性の判定は、第9図
に示すa、b2要素の場合、aの一端点であるa2から
一定のしきい値以内の距離にbの一端点b1が存在し、
かつaとbのなす角度θ(すなわちaの方向とbの方向
の差の絶対値)がある一定のしきい値以内の場合に連結
できる、とする。このようにして各要素を連結していき
、連結できた部分を破線として抽出する。
The direction determining section 4 determines the direction of the element from the coordinates of both end points of the element. Finally, in the connectivity determining section 5, connectivity of each element is determined. In the case of the a and b2 elements shown in FIG. 9, the above connectivity determination is performed if one end point b1 of b exists within a certain threshold distance from a2, which is one end point of a,
It is assumed that connection is possible when the angle θ formed by a and b (that is, the absolute value of the difference between the direction of a and the direction of b) is within a certain threshold. In this way, each element is connected, and the connected portion is extracted as a broken line.

発明が解決しようとする問題点 しかしながら上記のような構成では、細線化あるいは要
素の方向性判定等、複雑な処理のために処理時間が多く
かかり、また文字等の図形要素が画像上に混在する場合
には無駄な処理をするばかりか誤って上記図形要素を破
線の一部としてしまったり、さらには破線要素の連結性
の判定に一定の距離しきい値を用いているため、破線要
素の長さとその間隔の変化があった場合、破線要素をう
まくつなぐことができず、意図したようには破線の抽出
ができないといった問題があった〇本発明は上記問題点
に鑑み、高速で、直線や曲線等の他の線要素に加えて文
字等の図形要素が混在していてもよく、破線要素の長さ
及び間隔の変化に柔軟に対応できる破線抽出装置を提供
するものである。
Problems to be Solved by the Invention However, with the above configuration, a lot of processing time is required due to complicated processing such as thinning or determining the direction of elements, and graphical elements such as characters are mixed on the image. In some cases, not only is there unnecessary processing, but the above graphical elements are mistakenly included as part of the dashed line, and furthermore, because a fixed distance threshold is used to determine the connectivity of the dashed line elements, the length of the dashed line element is When there is a change in the distance between the dashed lines and the intervals between them, there is a problem that the dashed line elements cannot be connected well and the dashed line cannot be extracted as intended. In view of the above problems, the present invention has been developed to In addition to other line elements such as curves, graphic elements such as characters may be mixed, and the present invention provides a broken line extraction device that can flexibly respond to changes in the length and interval of broken line elements.

問題点を解決するための手段 上記問題点を解決するために、本発明の破線抽出装置は
、2次元平面上に表現される画像を2値化して入力する
読取部と、入力画像上で水平及び垂直方向の走査を行な
すて黒画素の連結成分を水平線、垂直線、斜線2文字及
び破線の構成要素である破線素に分類する線要素抽出部
と、破線素の連結性を分析して破線を認識する破線認識
部とを具備したものである。
Means for Solving the Problems In order to solve the above problems, the broken line extraction device of the present invention has a reading section that binarizes and inputs an image expressed on a two-dimensional plane, and a reading section that binarizes and inputs an image expressed on a two-dimensional plane. and a line element extraction unit that scans in the vertical direction and classifies the connected components of black pixels into horizontal lines, vertical lines, diagonal characters, and dashed line elements that are constituent elements of broken lines, and analyzes the connectivity of the dashed line elements. The present invention includes a broken line recognition unit that recognizes broken lines.

作  用 本発明は上含己した構成によって、直線や曲線等の他の
線要素に加えて文字等の混在した入力画像から、破線の
構成要素である破線素のみを抽出し、上記破線素の連結
性を適切に判定することによシ、高速かつ柔軟な破線抽
出を行なえることとなる。
Operation The present invention uses the above-mentioned configuration to extract only broken line elements that are constituent elements of a broken line from an input image containing characters, etc. in addition to other line elements such as straight lines and curves, and extracts only broken line elements that are constituent elements of broken lines. By appropriately determining connectivity, it is possible to perform fast and flexible dashed line extraction.

実施例 以下本発明の破線抽出装置の一実施例について、図面を
参照しながら説明する。
EXAMPLE Hereinafter, an example of the broken line extracting device of the present invention will be described with reference to the drawings.

第1図は本発明の実施例における破線抽出装置の構成を
示すものである。第1図において、11は制御部で破線
抽出装置全体の実行手順とデータの流れを制御する。1
2は読取部で紙などの二次元平面上に描かれた図形要素
を白黒の2値画像として入力する。13は被処理画像記
憶部で上記入力画像を2値データとして保持する。14
は線要素抽出部で黒画素領域の連結成分を水平線、垂直
線、斜線2文字及び破線の構成要素である破線素に分類
する。16は破線素記憶部であって、破線素のデータを
保持する。16は直線記憶部で水平線、垂直線、斜線の
データを保持する。17は破線認識部で16のデータの
連結性を判定して破線の認識を行ない、16のデータと
あわせて破線データを決定する。18は破線記憶部で破
線データを保持する。19は表示部で18のデータをも
とに破線の表示を行なう。
FIG. 1 shows the configuration of a broken line extraction device in an embodiment of the present invention. In FIG. 1, a control unit 11 controls the execution procedure and data flow of the entire broken line extraction device. 1
Reference numeral 2 denotes a reading unit which inputs graphic elements drawn on a two-dimensional plane such as paper as a black and white binary image. Reference numeral 13 denotes a processed image storage unit that stores the input image as binary data. 14
The line element extraction unit classifies the connected components of the black pixel area into horizontal lines, vertical lines, two characters with diagonal lines, and broken line elements that are constituent elements of broken lines. Reference numeral 16 denotes a broken line element storage unit, which holds data of broken line elements. Reference numeral 16 denotes a linear storage unit that holds data for horizontal lines, vertical lines, and diagonal lines. 17 is a broken line recognition unit that determines the connectivity of the data in 16, recognizes the broken line, and determines the broken line data together with the data in 16. 18 is a broken line storage unit that holds broken line data. A display section 19 displays a broken line based on the data 18.

以上のように構成された破線抽出装置について、以下第
1図、第2図、第3図、第4図、第6図。
The broken line extraction device configured as described above is shown in FIGS. 1, 2, 3, 4, and 6 below.

第6図及び第7図を用いてその動作を説明する。The operation will be explained using FIGS. 6 and 7.

第3図12の読取部で入力された2値画像は13の被処
理画像記憶部に保持される。この画像は14の線要素抽
出部においてまず水平方向及び垂直方向に一度ずつ走査
され、一定のしきい値以上の長さをもつ水平及び垂直方
向の黒画素の連続部分がそれぞれ水平線、垂直線として
検出される。この後、さらにもう一度水平走査を行ない
、水平線。
The binary image inputted by the reading section in FIG. 3 and 12 is held in the processed image storage section 13. This image is first scanned once in the horizontal and vertical directions in the 14 line element extraction units, and consecutive parts of black pixels in the horizontal and vertical directions with lengths longer than a certain threshold are extracted as horizontal lines and vertical lines, respectively. Detected. After this, perform another horizontal scan to find the horizon line.

垂直線以外の黒画素の連結領域を斜線2文字、破線素に
分類する。ここで斜線については単調な右上がりもしく
は右下がりである形状と、文字等に比して大きな領域を
占めることから容易に判別できるので、文字と破線素の
識別が問題となる。そこで水平線、垂直線、斜線以外の
連結黒領域一つずつについて、文字であるか破線素であ
るかの判定を行ない、破線素に分類されたものを15の
破線素記憶部のデータとして保持する。第4図は文字と
破線素の分類を示したもので、第4図aに示すように連
結黒画素領域中にループを持つものや、上下左右の4側
面のうち一つ以上の側面に深い(しきい値以上の)凹部
を持つものは文字に、そうでない第4図すに示すような
形状のものは破線素に分類する。本実施例では破線を水
平及び垂直方向のものに限定しているため、破線素の外
接矩形枠の形状により、破線素を水平方向の破線(以下
水平破線と呼ぶ)9構成要素である水平破線素と、垂直
方向の破線(以下垂直破線と呼ぶ)の構成要素である垂
直破線素と、水平破線と垂直破線の交点に生じる接続破
線素とに分類している。斜め方向の破線を考慮するなら
ば単調な右上がりか右下がりかを判定してその方向の破
線素に分類してもよい。また、水平線、垂直線、斜線の
データは第3図16の直線記憶部に保持される。
Connected areas of black pixels other than vertical lines are classified into two diagonal line characters and broken line elements. Here, diagonal lines can be easily distinguished because they have a monotonous upward or downward slope to the right and occupy a larger area than characters, so it becomes a problem to distinguish between characters and broken line elements. Therefore, for each connected black area other than horizontal lines, vertical lines, and diagonal lines, it is determined whether it is a character or a broken line element, and those classified as broken line elements are stored as data in the 15 broken line element storage units. . Figure 4 shows the classification of characters and dashed line elements.As shown in Figure 4a, there are those with loops in the connected black pixel area, and those with deep loops on one or more of the four sides of the top, bottom, left, and right. Those with concavities (above a threshold value) are classified as characters, and those with the shape shown in Figure 4 are classified as broken line elements. In this example, since broken lines are limited to those in the horizontal and vertical directions, the shape of the circumscribed rectangular frame of the broken line element allows the broken line element to be defined as a horizontal broken line (hereinafter referred to as horizontal broken line). vertical broken line elements, which are components of vertical broken lines (hereinafter referred to as vertical broken lines), and connected broken line elements that occur at the intersections of horizontal broken lines and vertical broken lines. If a dashed line in a diagonal direction is considered, it may be determined whether it is monotonous upward to the right or downward to the right and classified into dashed line elements in that direction. Further, data of horizontal lines, vertical lines, and diagonal lines are held in the linear storage section of FIG. 316.

線要素抽出部で抽出された水平線、垂直線、斜線及び各
破線素のデータは、以後2次元平面上の画素データをア
クセスする必要がないように、リスト化されたコード情
報となっている。第5図aに、水平破線素データの内容
を例として示す。
The data of horizontal lines, vertical lines, diagonal lines, and each broken line element extracted by the line element extraction section is code information listed so that there is no need to access pixel data on a two-dimensional plane thereafter. FIG. 5a shows an example of the contents of the horizontal broken line element data.

上記破線素のデータから、各破線素間の連結性を判定し
て破線の認識を行なうのが第3図17の破線認識部であ
る。水平破線と垂直破線の認識は同様の方法で行なうの
で、水平破線を例にとって説明する。全水平破線素を垂
直方向の座標値(以下y座標とする)の昇順にソートし
て、隣接2破線素間のy座標値の差がしきい値以下のも
のが一つのクラスタを構成するようにクラスタリングす
る。第6図は上記クラスタリングの様子を示す。
The broken line recognition unit shown in FIG. 317 recognizes broken lines by determining the connectivity between each broken line element from the data of the broken line elements. Horizontal broken lines and vertical broken lines are recognized using the same method, so the horizontal broken lines will be explained as an example. All horizontal dashed line elements are sorted in ascending order of their vertical coordinate values (hereinafter referred to as y coordinates), so that two adjacent dashed line elements whose y coordinate value difference is less than a threshold constitute one cluster. Clustering. FIG. 6 shows the above clustering.

この場合、全水平破線素はa、b、cの3つのクラスタ
に分類できる。次に同一クラスタ内の水平破線素を水平
方向の座標値(以下I座標とする)′の昇順にソートし
、隣接2破線素間の連結性を判定して、連結可能な部分
を一つの破線として認識する。第6図の場合には、al
 、a2.b、cの4つの破線が認識できる。
In this case, all horizontal dashed line elements can be classified into three clusters, a, b, and c. Next, the horizontal dashed line elements in the same cluster are sorted in ascending order of the horizontal coordinate value (hereinafter referred to as I coordinate)', the connectivity between two adjacent dashed line elements is determined, and the connectable parts are combined into one broken line. recognized as In the case of Figure 6, al
, a2. Four broken lines b and c can be recognized.

上記水平方向の連結性は、隣接2水平破線素のy座標の
差がしきい値以下であり、かつ第7図に示すような水平
方向の隣接2水平破線素の間隔と、間隔を含む全長との
比である白割合Wがしきい値以下の場合に連結可能であ
るとする。第6図においてm 、 nはどちらも水平破
線素であり、2.はmとnの間隔部分の水平方向の長さ
、2aはmとnそれぞれの水平方向の長さの和に2.を
加えたものである。破線データもリスト化コード情報と
して保持される。第5図すに例として水平破線データの
内容を示す。
The connectivity in the horizontal direction is such that the difference in the y-coordinates of two adjacent horizontal dashed line elements is equal to or less than a threshold value, and the distance between two adjacent horizontal dashed line elements in the horizontal direction and the total length including the interval as shown in FIG. It is assumed that connection is possible when the white ratio W, which is the ratio of In FIG. 6, m and n are both horizontal dashed line elements; 2. is the horizontal length of the space between m and n, and 2a is the sum of the horizontal lengths of m and n. is added. Broken line data is also held as listed code information. FIG. 5 shows the contents of horizontal broken line data as an example.

上記と同様にして垂直破線も認識したあと、接続破線素
を用いて破線の統合を行なう。第8図にその様子を示す
。接続破線素は水平破線と垂直破線の交点に生じるもの
なので、接続破線素の上下左右に白割合で連結できる範
囲内の水平破線及び垂直破線がどちらも最低1本ずつあ
る場合にのみ統合を行なう。
After vertical broken lines are also recognized in the same manner as above, the broken lines are integrated using connected broken line elements. Figure 8 shows the situation. Since a connected dashed line element occurs at the intersection of a horizontal broken line and a vertical broken line, integration is performed only when there is at least one horizontal broken line and one vertical broken line on both the top, bottom, left, and right sides of the connected dashed line element within the range that can be connected with the white ratio. .

統合がすんだ後にも構成破線素数が非常に少ない破線は
、実は単純な形状の文字が破線素として抽出されたもの
であると判断し、破線ではないものとして除去する。
Even after the integration is complete, it is determined that a dashed line that has very few component dashed line primes is actually a character with a simple shape extracted as a dashed line element, and is removed as not being a broken line.

最後に破線の端点、すなわち始終点を決定する。Finally, determine the end points of the broken line, that is, the start and end points.

原則として破線の端点けその破線を構成する破線素の両
端のものの端点て、近傍に連結破線素をもたない2端点
とするが、第9図に示すような場合、j、にの2本の破
線とも、作図者の意図としては垂直線pから始まるもの
とするのが妥当であるから、破線にの端点をp上に移動
することも可能である。端点付近に直交する実線あるい
は破線がない場合は、端点の移動は行なう必要はない。
In principle, the end points of a broken line and the end points of both ends of the broken line elements that make up the broken line should be two end points that have no connected broken line elements nearby, but in the case shown in Figure 9, the two end points of j and ni. Since it is reasonable for both dashed lines to start from the vertical line p, it is also possible to move the end points of the dashed lines above p. If there is no solid line or broken line perpendicular to the vicinity of the end point, there is no need to move the end point.

上記のよう忙して認識した破線のデータは第3図の18
破線記憶部に保持される。必要があれば19の表示部で
表示することができる。
The dashed line data recognized as busy as above is 18 in Figure 3.
It is held in the dashed line storage section. If necessary, it can be displayed on 19 display sections.

発明の効果 以上のように本発明は2次元平面上に表現される画像を
2値化して入力する読取部と、入力画像上で水平及び垂
直方向の走査を行なって黒画素の連結成分を水平線、垂
直線、斜線2文字及び破線の構成要素である破線素に分
類する線要素抽出部と、破線素の連結性を分析して破線
を認識する破線認識部とを設けることにより、直線や曲
線などの他の線要素だけでなく、文字等の図形要素の混
在する画像から高速かつ柔軟に破線を抽出することがで
きる。
Effects of the Invention As described above, the present invention includes a reading unit that binarizes and inputs an image expressed on a two-dimensional plane, and scans the input image in the horizontal and vertical directions to convert connected components of black pixels into horizontal lines. , by providing a line element extraction unit that classifies vertical lines, diagonal lines, two characters, and dashed lines into broken line elements that are constituent elements, and a broken line recognition unit that analyzes the connectivity of broken line elements and recognizes broken lines. Broken lines can be extracted quickly and flexibly from images containing not only other line elements such as characters, but also graphic elements such as characters.

【図面の簡単な説明】[Brief explanation of drawings]

第1図から第7図は本発明に関するものであり、第1図
は本発明の一実施例の構成図、第2図は文字と破線素の
判別を示す図、第3図は水平破線素及び水平破線のデー
タ内容の図、第4図は水平破線素のクラスタリングを示
す図、第5図は破線素の連結性判定のだめの白割合の図
、第6図は接続破線素を用いた破線の統合を示す図、第
7図は破線の端点決定の様子を示す図、第8図は従来例
の破線抽出装置の構成図、第9図は同装置の動作説明図
である。 11・・・・・・制御部、12・・・・・・読取部、1
3・・・・・・被処理画像記憶部、14・・・・・・線
要素抽出部、16・・・・・・破線未記憶部、16・・
・・・・直線記憶部、17・・・・・・破線認識部、1
8・・・・・・破線記憶部、19・・・・・・表示部。 代理人の氏名 弁理士 中 尾 敏 男 ほか1名第1
図 /’/ デ′−タθ纏ヒ爪 一−−−−−制御板 第2図 文字/+分り のイタ14 第3図 (C1) 第4図 一抹 ty海挟 第5図 yv211/j!^ 第6図 第7図
FIGS. 1 to 7 relate to the present invention. FIG. 1 is a block diagram of an embodiment of the present invention, FIG. 2 is a diagram showing discrimination between characters and broken line elements, and FIG. 3 is a diagram showing horizontal broken line elements. Figure 4 is a diagram showing clustering of horizontal dashed line elements, Figure 5 is a diagram of white percentage for determining connectivity of dashed line elements, and Figure 6 is a diagram of dashed lines using connected dashed line elements. 7 is a diagram showing how end points of broken lines are determined, FIG. 8 is a block diagram of a conventional broken line extraction device, and FIG. 9 is an explanatory diagram of the operation of the same device. 11...Control unit, 12...Reading unit, 1
3... Processed image storage section, 14... Line element extraction section, 16... Broken line unstored section, 16...
...Line storage section, 17...Dotted line recognition section, 1
8... Broken line storage section, 19... Display section. Name of agent: Patent attorney Toshio Nakao and 1 other person No. 1
Figure/'/ Data θ Wrapped in One ---- Control Board Figure 2 Letters/+Ita 14 Figure 3 (C1) Figure 4 One Sea Between Figure 5 Yv211/j! ^ Figure 6 Figure 7

Claims (1)

【特許請求の範囲】[Claims] 2次元平面上に表現される画像を2値化して入力する読
取部と、入力画像上で水平及び垂直方向の走査を行なっ
て黒画素の連結成分を水平線、垂直線、斜線、文字及び
破線の構成要素である破線素に分類する線要素抽出部と
、破線素の連結性を分析して破線を認識する破線認識部
とを備えたことを特徴とする破線抽出装置。
A reading unit that binarizes and inputs an image expressed on a two-dimensional plane, and a reading unit that scans the input image in the horizontal and vertical directions and converts connected components of black pixels into horizontal lines, vertical lines, diagonal lines, characters, and broken lines. What is claimed is: 1. A broken line extraction device comprising: a line element extraction unit that classifies broken line elements as constituent elements; and a broken line recognition unit that analyzes connectivity of the broken line elements and recognizes the broken line.
JP1788585A 1985-01-31 1985-01-31 Broken line extracting device Granted JPS61175880A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP1788585A JPS61175880A (en) 1985-01-31 1985-01-31 Broken line extracting device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP1788585A JPS61175880A (en) 1985-01-31 1985-01-31 Broken line extracting device

Publications (2)

Publication Number Publication Date
JPS61175880A true JPS61175880A (en) 1986-08-07
JPH0449148B2 JPH0449148B2 (en) 1992-08-10

Family

ID=11956157

Family Applications (1)

Application Number Title Priority Date Filing Date
JP1788585A Granted JPS61175880A (en) 1985-01-31 1985-01-31 Broken line extracting device

Country Status (1)

Country Link
JP (1) JPS61175880A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4810910A (en) * 1986-08-29 1989-03-07 Bull, S.A. Sense amplifier with bit-line derived clocking
JPH01113883A (en) * 1987-10-28 1989-05-02 Mitsubishi Electric Corp Method and device for input of line pattern
JPH01173178A (en) * 1987-12-26 1989-07-07 Fujitsu Ltd Extracting system for broken/dotted line string area
WO2010113217A1 (en) 2009-03-31 2010-10-07 富士通フロンテック株式会社 Character recognition device and character recognition method

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5636769A (en) * 1979-09-03 1981-04-10 Hitachi Ltd Line recognizing method of pattern recognition unit
JPS5638683A (en) * 1979-09-05 1981-04-13 Hitachi Ltd Discriminating method of type of line in pattern recognizer

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5636769A (en) * 1979-09-03 1981-04-10 Hitachi Ltd Line recognizing method of pattern recognition unit
JPS5638683A (en) * 1979-09-05 1981-04-13 Hitachi Ltd Discriminating method of type of line in pattern recognizer

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4810910A (en) * 1986-08-29 1989-03-07 Bull, S.A. Sense amplifier with bit-line derived clocking
JPH01113883A (en) * 1987-10-28 1989-05-02 Mitsubishi Electric Corp Method and device for input of line pattern
JPH01173178A (en) * 1987-12-26 1989-07-07 Fujitsu Ltd Extracting system for broken/dotted line string area
WO2010113217A1 (en) 2009-03-31 2010-10-07 富士通フロンテック株式会社 Character recognition device and character recognition method
US8577147B2 (en) 2009-03-31 2013-11-05 Fujitsu Frontech Limited Character recognition apparatus and character recognition method

Also Published As

Publication number Publication date
JPH0449148B2 (en) 1992-08-10

Similar Documents

Publication Publication Date Title
US6798895B1 (en) Character string extraction and image processing methods and apparatus
JPH0721310A (en) Document recognizing device
JPH0418351B2 (en)
JPS61175880A (en) Broken line extracting device
JP2890306B2 (en) Table space separation apparatus and table space separation method
JP3476595B2 (en) Image area division method and image binarization method
JPH06187489A (en) Character recognizing device
JP7283756B2 (en) Information processing device and program
JPH0573718A (en) Area attribute identifying system
JPH02253383A (en) Picture processor
JPH03142691A (en) Table format document recognizing system
JP2643960B2 (en) Character recognition method
JPH03268181A (en) Document reader
JPH0697470B2 (en) Character string extractor
JP3104355B2 (en) Feature extraction device
JPS63157287A (en) Character pattern extracting method
JPH0721309A (en) Document recognizing device
JP2571826B2 (en) String pattern extraction device
JPH11306282A (en) Method and device for extracting character string area
JPH01149184A (en) Character area extracting system
JPH0334081A (en) Drawing reader
JPH06131496A (en) Pattern normalization processing method
JPH0628520A (en) Character recognition device
JPH01140274A (en) Character row recognition system
JPH0146913B2 (en)